Downloads · 30 days
8
2% of all-time downloads
finetuned_distilbert_fa_zwnj_base_ner
mehdidn/finetuned_distilbert_fa_zwnj_base_ner
finetuned_distilbert_fa_zwnj_base_ner is a token classification model from mehdidn. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
410
Public
Repo size
2.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin301 MB · 99%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- distilbert
- Access
- Public
- Created
- Sep 3, 2022
- Updated
- Sep 22, 2022
- SHA
- 9db3423a
Try a prompt
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
finetuned_distilbert_fa_zwnj_base_ner
This model is a fine-tuned version of HooshvareLab/distilbert-fa-zwnj-base on the mixed NER dataset collected from ARMAN, PEYMA, and WikiANN. It achieves the following results on the evaluation set:
- Loss: 0.0343
- Precision: 0.9416
- Recall: 0.9549
- F1: 0.9482
- Accuracy: 0.9938
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.1456 | 1.0 | 1821 | 0.0699 | 0.7847 | 0.8037 | 0.7941 | 0.9773 |
| 0.0551 | 2.0 | 3642 | 0.0456 | 0.8574 | 0.8875 | 0.8722 | 0.9858 |
| 0.0283 | 3.0 | 5463 | 0.0333 | 0.8957 | 0.9225 | 0.9089 | 0.9902 |
| 0.0161 | 4.0 | 7284 | 0.0299 | 0.9229 | 0.9374 | 0.9301 | 0.9921 |
| 0.0103 | 5.0 | 9105 | 0.0298 | 0.9314 | 0.9471 | 0.9392 | 0.9929 |
| 0.0069 | 6.0 | 10926 | 0.0323 | 0.9305 | 0.9513 | 0.9408 | 0.9930 |
| 0.0045 | 7.0 | 12747 | 0.0337 | 0.9363 | 0.9510 | 0.9436 | 0.9933 |
| 0.0031 | 8.0 | 14568 | 0.0339 | 0.9395 | 0.9526 | 0.9460 | 0.9937 |
| 0.0024 | 9.0 | 16389 | 0.0334 | 0.9392 | 0.9545 | 0.9468 | 0.9938 |
| 0.0017 | 10.0 | 18210 | 0.0343 | 0.9416 | 0.9549 | 0.9482 | 0.9938 |
Framework versions
- Transformers 4.21.2
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1
- Task
- Token Classification
- Library
- transformers
- Type
- distilbert
- License
- apache-2.0
- Created
- Sep 3, 2022
- Updated
- Sep 22, 2022